Are GANs Created Equal? A Large-Scale Study · HackerPapers discussions

Are GANs Created Equal? A Large-Scale Study — HN submission

Tue, 23 Jul 2019 10:50:29 GMT

Are GANs Created Equal? A Large-Scale Study (2017)

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Are GANs Created Equal? A Large-Scale Study — mentioned by tasdfqwer0897

Wed, 10 Apr 2019 02:58:06 GMT

Hmm, I'm not sure what you mean by applicable loss functions? I'll answer what I think you're asking and you can tell me if I got it wrong: There's been a lot of effort spent on coming up with different loss functions for GANs, but https://arxiv.org/abs/1711.10337 shows that, according to the metrics in problem 5, they don't really improve results compared to the original GAN loss function. There's something called a Wasserstein GAN https://arxiv.org/abs/1701.07875 that you may have heard about, but IMO the useful thing to take away from that paper is their 'gradient penalty' technique and…

Paper and discussion history. A mention is not an endorsement.

Are GANs Created Equal? A Large-Scale Study — HN submission

Wed, 29 Nov 2017 07:26:47 GMT

Are GANs Created Equal? A Large-Scale Study

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.